Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors

Freezing of Gait (FoG) is a disabling motor symptom that characterizes Parkinson’s Disease (PD) patients and significantly affects their mobility and quality of life. The paper presents a novel hybrid deep learning framework for the detection of FoG episodes using wearable sensors. The methodology c...

Full description

Saved in:
Bibliographic Details
Main Authors: Mosleh Hmoud Al-Adhaileh, Asim Wadood, Theyazn H. H. Aldhyani, Safeer Khan, M. Irfan Uddin, Abdullah H. Al-Nefaie
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Physiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphys.2025.1581699/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712252606742528
author Mosleh Hmoud Al-Adhaileh
Mosleh Hmoud Al-Adhaileh
Asim Wadood
Theyazn H. H. Aldhyani
Theyazn H. H. Aldhyani
Safeer Khan
M. Irfan Uddin
Abdullah H. Al-Nefaie
Abdullah H. Al-Nefaie
author_facet Mosleh Hmoud Al-Adhaileh
Mosleh Hmoud Al-Adhaileh
Asim Wadood
Theyazn H. H. Aldhyani
Theyazn H. H. Aldhyani
Safeer Khan
M. Irfan Uddin
Abdullah H. Al-Nefaie
Abdullah H. Al-Nefaie
author_sort Mosleh Hmoud Al-Adhaileh
collection DOAJ
description Freezing of Gait (FoG) is a disabling motor symptom that characterizes Parkinson’s Disease (PD) patients and significantly affects their mobility and quality of life. The paper presents a novel hybrid deep learning framework for the detection of FoG episodes using wearable sensors. The methodology combines CNNs for spatial feature extraction, BiLSTM networks for temporal modeling, and an attention mechanism to enhance interpretability and focus on critical gait features. The approach leverages multimodal datasets, including tDCS FOG, DeFOG, Daily Living, and Hantao’s Multimodal, to ensure robustness and generalizability. The proposed model deals with sensor noise, inter-subject variability, and data imbalance through comprehensive preprocessing techniques such as sensor fusion, normalization, and data augmentation. The proposed model achieved an average accuracy of 92.5%, F1-score of 89.3%, and AUC of 0.91, outperforming state-of-the-art methods. Post-training quantization and pruning enabled deployment on edge devices such as Raspberry Pi and Coral TPU, achieving inference latency under 350 ms. Ablation studies show the critical contribution of key architectural components to the model’s effectiveness. Optimized to be deployed real-time, it is a potentially promising solution that can help correctly detect FoG, thereby achieving better clinical monitoring and improving patients’ outcomes in a controlled as well as real world.
format Article
id doaj-art-967967f7fd5048aca9bc3cbf8a45477a
institution DOAJ
issn 1664-042X
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physiology
spelling doaj-art-967967f7fd5048aca9bc3cbf8a45477a2025-08-20T03:14:20ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-05-011610.3389/fphys.2025.15816991581699Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensorsMosleh Hmoud Al-Adhaileh0Mosleh Hmoud Al-Adhaileh1Asim Wadood2Theyazn H. H. Aldhyani3Theyazn H. H. Aldhyani4Safeer Khan5M. Irfan Uddin6Abdullah H. Al-Nefaie7Abdullah H. Al-Nefaie8King Salman Center for Disability Research, Riyadh, Saudi ArabiaDeanship of E-Learning and Information Technology, King Faisal University, Al-Ahsa, Saudi ArabiaInstitute of Computing, Kohat University of Science and Technology, Kohat, PakistanKing Salman Center for Disability Research, Riyadh, Saudi ArabiaApplied College in Abqaiq, King Faisal University, Al-Ahsa, Saudi ArabiaInstitute of Computing, Kohat University of Science and Technology, Kohat, PakistanInstitute of Computing, Kohat University of Science and Technology, Kohat, PakistanKing Salman Center for Disability Research, Riyadh, Saudi ArabiaDepartment of Quantitative Methods, School of Business, King Faisal University, Al-Ahsa, Saudi ArabiaFreezing of Gait (FoG) is a disabling motor symptom that characterizes Parkinson’s Disease (PD) patients and significantly affects their mobility and quality of life. The paper presents a novel hybrid deep learning framework for the detection of FoG episodes using wearable sensors. The methodology combines CNNs for spatial feature extraction, BiLSTM networks for temporal modeling, and an attention mechanism to enhance interpretability and focus on critical gait features. The approach leverages multimodal datasets, including tDCS FOG, DeFOG, Daily Living, and Hantao’s Multimodal, to ensure robustness and generalizability. The proposed model deals with sensor noise, inter-subject variability, and data imbalance through comprehensive preprocessing techniques such as sensor fusion, normalization, and data augmentation. The proposed model achieved an average accuracy of 92.5%, F1-score of 89.3%, and AUC of 0.91, outperforming state-of-the-art methods. Post-training quantization and pruning enabled deployment on edge devices such as Raspberry Pi and Coral TPU, achieving inference latency under 350 ms. Ablation studies show the critical contribution of key architectural components to the model’s effectiveness. Optimized to be deployed real-time, it is a potentially promising solution that can help correctly detect FoG, thereby achieving better clinical monitoring and improving patients’ outcomes in a controlled as well as real world.https://www.frontiersin.org/articles/10.3389/fphys.2025.1581699/fullwearable sensorfreezing of gaitdeep learningattention mechanismartifcial intelligence
spellingShingle Mosleh Hmoud Al-Adhaileh
Mosleh Hmoud Al-Adhaileh
Asim Wadood
Theyazn H. H. Aldhyani
Theyazn H. H. Aldhyani
Safeer Khan
M. Irfan Uddin
Abdullah H. Al-Nefaie
Abdullah H. Al-Nefaie
Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
Frontiers in Physiology
wearable sensor
freezing of gait
deep learning
attention mechanism
artifcial intelligence
title Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
title_full Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
title_fullStr Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
title_full_unstemmed Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
title_short Deep learning techniques for detecting freezing of gait episodes in Parkinson’s disease using wearable sensors
title_sort deep learning techniques for detecting freezing of gait episodes in parkinson s disease using wearable sensors
topic wearable sensor
freezing of gait
deep learning
attention mechanism
artifcial intelligence
url https://www.frontiersin.org/articles/10.3389/fphys.2025.1581699/full
work_keys_str_mv AT moslehhmoudaladhaileh deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT moslehhmoudaladhaileh deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT asimwadood deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT theyaznhhaldhyani deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT theyaznhhaldhyani deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT safeerkhan deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT mirfanuddin deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT abdullahhalnefaie deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors
AT abdullahhalnefaie deeplearningtechniquesfordetectingfreezingofgaitepisodesinparkinsonsdiseaseusingwearablesensors